# Dataset Configuration
import os

# Dataset parameters
endpoint_url = "https://idsm.elixir-czech.cz/sparql/endpoint/idsm"
dataset_name = "pubchem.protein"
void_iri = "http://rdf.ncbi.nlm.nih.gov/pubchem/protein"
graph_uri = "http://rdf.ncbi.nlm.nih.gov/pubchem/protein"

# Setup paths
working_path = os.path.abspath("")
exports_path = os.path.join(
    working_path, "..", "..", "docs", "data", "schema_extraction", dataset_name
)
os.makedirs(exports_path, exist_ok=True)

import logging
import sys

# Minimal notebook logger using existing dataset_name
logger = logging.getLogger(dataset_name or "notebook")
logger.setLevel(logging.DEBUG)  # Set to DEBUG to see SPARQL queries

# Also configure the rdfsolve.parser logger to see query details
parser_logger = logging.getLogger("rdfsolve.parser")
parser_logger.setLevel(logging.DEBUG)

# Avoid adding duplicate handlers if the cell is re-run
if not logger.handlers:
    fmt = logging.Formatter("%(asctime)s %(levelname)s %(name)s: %(message)s", "%Y-%m-%d %H:%M:%S")

    sh = logging.StreamHandler(sys.stdout)
    sh.setLevel(logging.DEBUG)  # Set to DEBUG to see all logs
    sh.setFormatter(fmt)
    logger.addHandler(sh)

    # Add the same handler to the parser logger
    parser_logger.addHandler(sh)

logger.info(f"Logging configured for {dataset_name}")

2025-12-02 10:11:06 INFO pubchem.protein: Logging configured for pubchem.protein

# Import libraries
import json

# Configure Plotly for HTML output
import plotly.io as pio
import plotly.offline as pyo
from IPython.display import Markdown, display

# Import rdfsolve API functions
from rdfsolve.api import (
    discover_void_graphs,
    generate_void_from_endpoint,
    load_parser_from_graph,
    retrieve_void_from_graphs,
)
from rdfsolve.sparql_helper import SparqlHelper

# Enable query collection to track all SPARQL queries executed
SparqlHelper.enable_query_collection()

# Set renderer to 'notebook' for Jupyter, but ensure HTML export works
pio.renderers.default = "notebook+plotly_mimetype"

# Initialize offline mode for Plotly
pyo.init_notebook_mode(connected=True)

# Pickle caching utilities
import os
import pickle


def save_cache(data, filename, cache_dir=None):
    """Save data to pickle cache."""
    if cache_dir is None:
        cache_dir = os.path.join(exports_path, "cache")
    os.makedirs(cache_dir, exist_ok=True)

    cache_path = os.path.join(cache_dir, f"{filename}.pkl")
    with open(cache_path, "wb") as f:
        pickle.dump(data, f)
    print(f"Cached data to: {cache_path}")
    return cache_path


def load_cache(filename, cache_dir=None):
    """Load data from pickle cache if it exists."""
    if cache_dir is None:
        cache_dir = os.path.join(exports_path, "cache")

    cache_path = os.path.join(cache_dir, f"{filename}.pkl")
    if os.path.exists(cache_path):
        with open(cache_path, "rb") as f:
            data = pickle.load(f)
        print(f"Loaded cached data from: {cache_path}")
        return data
    return None


def cache_exists(filename, cache_dir=None):
    """Check if cache file exists."""
    if cache_dir is None:
        cache_dir = os.path.join(exports_path, "cache")

    cache_path = os.path.join(cache_dir, f"{filename}.pkl")
    return os.path.exists(cache_path)

# Cache management utilities
def list_cache_files(cache_dir=None):
    """List all cache files."""
    if cache_dir is None:
        cache_dir = os.path.join(exports_path, "cache")

    if not os.path.exists(cache_dir):
        print("No cache directory found")
        return []

    cache_files = [f for f in os.listdir(cache_dir) if f.endswith(".pkl")]
    print(f"Cache directory: {cache_dir}")
    for f in cache_files:
        file_path = os.path.join(cache_dir, f)
        size_mb = os.path.getsize(file_path) / (1024 * 1024)
        print(f"  {f} ({size_mb:.2f} MB)")
    return cache_files


def clear_cache(filename=None, cache_dir=None):
    """Clear specific cache file or all cache."""
    if cache_dir is None:
        cache_dir = os.path.join(exports_path, "cache")

    if filename:
        cache_path = os.path.join(cache_dir, f"{filename}.pkl")
        if os.path.exists(cache_path):
            os.remove(cache_path)
            print(f"Removed cache: {filename}")
        else:
            print(f"Cache not found: {filename}")
    else:
        # Clear all cache files
        if os.path.exists(cache_dir):
            import shutil

            shutil.rmtree(cache_dir)
            print("Cleared all cache files")
        else:
            print("No cache directory to clear")


# Show current cache status
list_cache_files()

No cache directory found

[]

# Clear specific cache files (uncomment lines as needed for testing)

# When testing new VoID discovery/generation:
# clear_cache(f"{dataset_name}_voidgraph")

# When testing JSON-LD generation (primary output):
# clear_cache(f"{dataset_name}_jsonld_schema")

# When testing frequency calculations:
# clear_cache(f"{dataset_name}_frequencies_basic")
# clear_cache(f"{dataset_name}_frequencies_with_instances")

# Clear everything:
clear_cache()

print("Cache control ready")
print("Note: VoID graph and JSON-LD are the primary caches")

No cache directory to clear
Cache control ready
Note: VoID graph and JSON-LD are the primary caches

# Discover or generate VoID schema with caching
cache_key = f"{dataset_name}_voidgraph"

# Try to load from cache first
void_graph = load_cache(cache_key)

if void_graph is None:
    print("VoID graph not found in cache, attempting discovery...")

    # Step 1: Try to discover existing VoID graphs
    discovery_result = discover_void_graphs(
        endpoint_url, graph_uris=[graph_uri] if graph_uri else None
    )

    found_graphs = discovery_result.get("found_graphs", [])
    partitions = discovery_result.get("partitions", [])

    if found_graphs and partitions:
        print(f"Found {len(found_graphs)} VoID graphs with {len(partitions)} partitions")
        # Build VoID graph directly from partition data (no CONSTRUCT query needed)
        void_graph = retrieve_void_from_graphs(
            endpoint_url,
            found_graphs,
            graph_uris=[graph_uri] if graph_uri else None,
            partitions=partitions,  # Pass partition data directly
        )

        # Save to file
        void_path = os.path.join(exports_path, f"{dataset_name}_existing_void.ttl")
        void_graph.serialize(destination=void_path, format="turtle")
        print(f"Built VoID graph from: {', '.join(found_graphs)}")
    else:
        print("No VoID graphs found, generating from queries...")
        # Step 2: Generate new VoID if none found
        void_graph = generate_void_from_endpoint(
            endpoint_url=endpoint_url,
            graph_uris=[graph_uri] if graph_uri else None,
            output_file=os.path.join(exports_path, f"{dataset_name}_generated_void.ttl"),
            counts=True,
            offset_limit_steps=300,
            exclude_graphs=True,
        )

    # Cache the VoID graph for future use
    save_cache(void_graph, cache_key)
    print(f"VoID graph cached with {len(void_graph)} triples")
else:
    print(f"Loaded VoID graph from cache ({len(void_graph)} triples)")

# Load parser from the VoID graph
vp = load_parser_from_graph(void_graph, graph_uris=[graph_uri] if graph_uri else None)

VoID graph not found in cache, attempting discovery...
2025-12-02 10:11:07 DEBUG rdfsolve.parser: Starting VoID partition discovery for https://idsm.elixir-czech.cz/sparql/endpoint/idsm

2025-12-02 10:11:07 INFO rdfsolve.parser: Discovering VoID partitions across all graphs

Query attempt 1/3 failed: 500 Server Error: 500 for url: https://idsm.elixir-czech.cz/sparql/endpoint/idsm?query=%0A++++++++PREFIX+void%3A+%3Chttp%3A%2F%2Frdfs.org%2Fns%2Fvoid%23%3E%0A++++++++PREFIX+void-ext%3A+%3Chttp%3A%2F%2Fldf.fi%2Fvoid-ext%23%3E%0A++++++++SELECT+DISTINCT+%3FsubjectClass+%3Fprop+%3FobjectClass+%3FobjectDatatype+%3Fg%0A++++++++WHERE+%7B%0A++++++++++GRAPH+%3Fg+%7B%0A++++++++++++%7B%0A++++++++++++++%3Fcp+void%3Aclass+%3FsubjectClass+%3B%0A++++++++++++++++++void%3ApropertyPartition+%3Fpp+.%0A++++++++++++++%3Fpp+void%3Aproperty+%3Fprop+.%0A++++++++++++++OPTIONAL+%7B%0A++++++++++++++++++%7B%0A++++++++++++++++++++++%3Fpp++void%3AclassPartition+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++++++++%7D+UNION+%7B%0A++++++++++++++++++++++%3Fpp+void-ext%3AdatatypePartition+%5B+void-ext%3Adatatype+%3FobjectDatatype+%5D+.%0A++++++++++++++++++%7D%0A++++++++++++++%7D%0A++++++++++++%7D+UNION+%7B%0A++++++++++++++%3Fls+void%3AsubjectsTarget+%5B+void%3Aclass+%3FsubjectClass+%5D+%3B%0A++++++++++++++++++void%3AlinkPredicate+%3Fprop+%3B%0A++++++++++++++++++void%3AobjectsTarget+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++%7D%0A++++++++++%7D%0A++++++++%7D%0A++++++++

Query attempt 2/3 failed: 500 Server Error: 500 for url: https://idsm.elixir-czech.cz/sparql/endpoint/idsm?query=%0A++++++++PREFIX+void%3A+%3Chttp%3A%2F%2Frdfs.org%2Fns%2Fvoid%23%3E%0A++++++++PREFIX+void-ext%3A+%3Chttp%3A%2F%2Fldf.fi%2Fvoid-ext%23%3E%0A++++++++SELECT+DISTINCT+%3FsubjectClass+%3Fprop+%3FobjectClass+%3FobjectDatatype+%3Fg%0A++++++++WHERE+%7B%0A++++++++++GRAPH+%3Fg+%7B%0A++++++++++++%7B%0A++++++++++++++%3Fcp+void%3Aclass+%3FsubjectClass+%3B%0A++++++++++++++++++void%3ApropertyPartition+%3Fpp+.%0A++++++++++++++%3Fpp+void%3Aproperty+%3Fprop+.%0A++++++++++++++OPTIONAL+%7B%0A++++++++++++++++++%7B%0A++++++++++++++++++++++%3Fpp++void%3AclassPartition+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++++++++%7D+UNION+%7B%0A++++++++++++++++++++++%3Fpp+void-ext%3AdatatypePartition+%5B+void-ext%3Adatatype+%3FobjectDatatype+%5D+.%0A++++++++++++++++++%7D%0A++++++++++++++%7D%0A++++++++++++%7D+UNION+%7B%0A++++++++++++++%3Fls+void%3AsubjectsTarget+%5B+void%3Aclass+%3FsubjectClass+%5D+%3B%0A++++++++++++++++++void%3AlinkPredicate+%3Fprop+%3B%0A++++++++++++++++++void%3AobjectsTarget+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++%7D%0A++++++++++%7D%0A++++++++%7D%0A++++++++

Query attempt 3/3 failed: 500 Server Error: 500 for url: https://idsm.elixir-czech.cz/sparql/endpoint/idsm?query=%0A++++++++PREFIX+void%3A+%3Chttp%3A%2F%2Frdfs.org%2Fns%2Fvoid%23%3E%0A++++++++PREFIX+void-ext%3A+%3Chttp%3A%2F%2Fldf.fi%2Fvoid-ext%23%3E%0A++++++++SELECT+DISTINCT+%3FsubjectClass+%3Fprop+%3FobjectClass+%3FobjectDatatype+%3Fg%0A++++++++WHERE+%7B%0A++++++++++GRAPH+%3Fg+%7B%0A++++++++++++%7B%0A++++++++++++++%3Fcp+void%3Aclass+%3FsubjectClass+%3B%0A++++++++++++++++++void%3ApropertyPartition+%3Fpp+.%0A++++++++++++++%3Fpp+void%3Aproperty+%3Fprop+.%0A++++++++++++++OPTIONAL+%7B%0A++++++++++++++++++%7B%0A++++++++++++++++++++++%3Fpp++void%3AclassPartition+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++++++++%7D+UNION+%7B%0A++++++++++++++++++++++%3Fpp+void-ext%3AdatatypePartition+%5B+void-ext%3Adatatype+%3FobjectDatatype+%5D+.%0A++++++++++++++++++%7D%0A++++++++++++++%7D%0A++++++++++++%7D+UNION+%7B%0A++++++++++++++%3Fls+void%3AsubjectsTarget+%5B+void%3Aclass+%3FsubjectClass+%5D+%3B%0A++++++++++++++++++void%3AlinkPredicate+%3Fprop+%3B%0A++++++++++++++++++void%3AobjectsTarget+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++%7D%0A++++++++++%7D%0A++++++++%7D%0A++++++++

SELECT failed after 3 tries

2025-12-02 10:11:12 INFO rdfsolve.parser: VoID discovery failed: Query failed after 3 attempts: 500 Server Error: 500 for url: https://idsm.elixir-czech.cz/sparql/endpoint/idsm?query=%0A++++++++PREFIX+void%3A+%3Chttp%3A%2F%2Frdfs.org%2Fns%2Fvoid%23%3E%0A++++++++PREFIX+void-ext%3A+%3Chttp%3A%2F%2Fldf.fi%2Fvoid-ext%23%3E%0A++++++++SELECT+DISTINCT+%3FsubjectClass+%3Fprop+%3FobjectClass+%3FobjectDatatype+%3Fg%0A++++++++WHERE+%7B%0A++++++++++GRAPH+%3Fg+%7B%0A++++++++++++%7B%0A++++++++++++++%3Fcp+void%3Aclass+%3FsubjectClass+%3B%0A++++++++++++++++++void%3ApropertyPartition+%3Fpp+.%0A++++++++++++++%3Fpp+void%3Aproperty+%3Fprop+.%0A++++++++++++++OPTIONAL+%7B%0A++++++++++++++++++%7B%0A++++++++++++++++++++++%3Fpp++void%3AclassPartition+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++++++++%7D+UNION+%7B%0A++++++++++++++++++++++%3Fpp+void-ext%3AdatatypePartition+%5B+void-ext%3Adatatype+%3FobjectDatatype+%5D+.%0A++++++++++++++++++%7D%0A++++++++++++++%7D%0A++++++++++++%7D+UNION+%7B%0A++++++++++++++%3Fls+void%3AsubjectsTarget+%5B+void%3Aclass+%3FsubjectClass+%5D+%3B%0A++++++++++++++++++void%3AlinkPredicate+%3Fprop+%3B%0A++++++++++++++++++void%3AobjectsTarget+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++%7D%0A++++++++++%7D%0A++++++++%7D%0A++++++++

2025-12-02 10:11:12 DEBUG rdfsolve.parser: Discovery exception: EndpointError: Query failed after 3 attempts: 500 Server Error: 500 for url: https://idsm.elixir-czech.cz/sparql/endpoint/idsm?query=%0A++++++++PREFIX+void%3A+%3Chttp%3A%2F%2Frdfs.org%2Fns%2Fvoid%23%3E%0A++++++++PREFIX+void-ext%3A+%3Chttp%3A%2F%2Fldf.fi%2Fvoid-ext%23%3E%0A++++++++SELECT+DISTINCT+%3FsubjectClass+%3Fprop+%3FobjectClass+%3FobjectDatatype+%3Fg%0A++++++++WHERE+%7B%0A++++++++++GRAPH+%3Fg+%7B%0A++++++++++++%7B%0A++++++++++++++%3Fcp+void%3Aclass+%3FsubjectClass+%3B%0A++++++++++++++++++void%3ApropertyPartition+%3Fpp+.%0A++++++++++++++%3Fpp+void%3Aproperty+%3Fprop+.%0A++++++++++++++OPTIONAL+%7B%0A++++++++++++++++++%7B%0A++++++++++++++++++++++%3Fpp++void%3AclassPartition+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++++++++%7D+UNION+%7B%0A++++++++++++++++++++++%3Fpp+void-ext%3AdatatypePartition+%5B+void-ext%3Adatatype+%3FobjectDatatype+%5D+.%0A++++++++++++++++++%7D%0A++++++++++++++%7D%0A++++++++++++%7D+UNION+%7B%0A++++++++++++++%3Fls+void%3AsubjectsTarget+%5B+void%3Aclass+%3FsubjectClass+%5D+%3B%0A++++++++++++++++++void%3AlinkPredicate+%3Fprop+%3B%0A++++++++++++++++++void%3AobjectsTarget+%5B+void%3Aclass+%3FobjectClass+%5D+.%0A++++++++++++%7D%0A++++++++++%7D%0A++++++++%7D%0A++++++++

No VoID graphs found, generating from queries...

2025-12-02 10:11:19 INFO rdfsolve.parser: Successfully extracted 770 RDF triples

# Primary JSON-LD schema export and basic summary
cache_key = f"{dataset_name}_jsonld_schema"
jsonld_schema = load_cache(cache_key)

if jsonld_schema is None:
    print("Generating JSON-LD schema...")
    jsonld_schema = vp.to_jsonld(filter_void_admin_nodes=True)
    save_cache(jsonld_schema, cache_key)
else:
    print("Loaded JSON-LD schema from cache")

# Save JSON-LD schema file
jsonld_file = os.path.join(exports_path, f"{dataset_name}_schema.jsonld")
with open(jsonld_file, "w", encoding="utf-8") as f:
    json.dump(jsonld_schema, f, indent=2, ensure_ascii=False)

print(f"JSON-LD Schema saved to: {jsonld_file}")

# Display combined JSON-LD structure info and schema summary
if "@graph" in jsonld_schema:
    print("\nSchema Summary:")
    print(f"   • Prefixes: {len(jsonld_schema['@context'])}")
    print(f"   • Resources: {len(jsonld_schema['@graph'])}")

    # Show dataset metadata
    dataset_info = jsonld_schema["@graph"][0] if jsonld_schema["@graph"] else {}
    if dataset_info.get("@type") == "void:Dataset":
        print(f"   • Dataset: {dataset_info.get('dcterms:title', 'Unknown')}")
        print(f"   • Classes: {dataset_info.get('void:classes', 0)}")
        print(f"   • Properties: {dataset_info.get('void:properties', 0)}")
        print(f"   • Triples: {dataset_info.get('void:triples', 0)}")

# Get schema DataFrame and show sample
schema_df = vp.to_schema(filter_void_admin_nodes=True)
print(f"\nSchema Patterns Preview ({len(schema_df)} total):")
display(schema_df.head())

Generating JSON-LD schema...

Cached data to: /home/runner/work/rdfsolve/rdfsolve/notebooks/01_schema_extraction/../../docs/data/schema_extraction/pubchem.protein/cache/pubchem.protein_jsonld_schema.pkl
JSON-LD Schema saved to: /home/runner/work/rdfsolve/rdfsolve/notebooks/01_schema_extraction/../../docs/data/schema_extraction/pubchem.protein/pubchem.protein_schema.jsonld

Schema Summary:
   • Prefixes: 5
   • Resources: 202

Schema Patterns Preview (42218 total):

# Schema pattern coverage analysis and export
cache_key = f"{dataset_name}_frequencies_basic"
cached_data = load_cache(cache_key)

if cached_data is None:
    print("Calculating schema pattern frequencies...")
    frequencies_df, _ = vp.count_schema_shape_frequencies(
        endpoint_url=endpoint_url,
        offset_limit_steps=300,
    )
    save_cache(frequencies_df, cache_key)
else:
    print("Loaded frequencies DataFrame from cache")
    frequencies_df = cached_data

# Export coverage analysis
frequencies_output_path = os.path.join(exports_path, f"{dataset_name}_pattern_coverage.csv")
exported_df = vp.export_schema_shape_frequencies(
    frequencies_df, output_file=frequencies_output_path
)

# Combined summary and sample
if not frequencies_df.empty:
    avg_coverage = frequencies_df["coverage_percent"].mean()
    high_coverage = (frequencies_df["coverage_percent"] > 50).sum()

    print("\nPattern Coverage Analysis:")
    print(f"   • Total patterns: {len(frequencies_df)}")
    print(f"   • Average coverage: {avg_coverage:.1f}%")
    print(f"   • High coverage (>50%): {high_coverage}")
    print(f"   • Exported to: {frequencies_output_path}")

    print("\nSample Coverage Data:")
    display(
        frequencies_df[["subject_class", "property", "object_class", "coverage_percent"]].head()
    )

    print("\nCoverage Statistics:")
    display(frequencies_df["coverage_percent"].describe())
else:
    print("No frequency data available")

Calculating schema pattern frequencies...

2025-12-02 10:11:36 INFO rdfsolve.parser: Using chunked pagination for entity counts (step size: 300)

INFO:rdfsolve.parser:Using chunked pagination for entity counts (step size: 300)

2025-12-02 10:11:37 DEBUG rdfsolve.parser: Chunked entity count: chunk 1, rows=300, total=300

DEBUG:rdfsolve.parser:Chunked entity count: chunk 1, rows=300, total=300

2025-12-02 10:11:49 DEBUG rdfsolve.parser: Chunked entity count: chunk 2, rows=300, total=600

DEBUG:rdfsolve.parser:Chunked entity count: chunk 2, rows=300, total=600

2025-12-02 10:12:00 DEBUG rdfsolve.parser: Chunked entity count: chunk 3, rows=300, total=900

DEBUG:rdfsolve.parser:Chunked entity count: chunk 3, rows=300, total=900

2025-12-02 10:12:11 DEBUG rdfsolve.parser: Chunked entity count: chunk 4, rows=300, total=1200

# Collect both frequency data and actual instances with caching
cache_key = f"{dataset_name}_frequencies_with_instances"
cached_data = load_cache(cache_key)

if cached_data is None:
    print("Collecting frequency data and instances...")
    frequencies_with_instances_df, instances_df = vp.count_schema_shape_frequencies(
        endpoint_url=endpoint_url,
        # sample_limit=100,  # Limited sample for demonstration
        collect_instances=True,
        offset_limit_steps=300,
    )
    # Cache both DataFrames as a tuple
    save_cache((frequencies_with_instances_df, instances_df), cache_key)
else:
    print("Loaded frequencies and instances DataFrames from cache")
    frequencies_with_instances_df, instances_df = cached_data

# Display basic information about the data structure
print(f"Frequencies DataFrame: {len(frequencies_with_instances_df)} shapes")
if frequencies_with_instances_df is not None:
    print(
        f"Memory usage - Instances: {frequencies_with_instances_df.memory_usage(deep=True).sum() / 1024:.1f} KB"
    )
else:
    print("No instances collected")

Collecting frequency data and instances...

2025-12-02 11:33:22 INFO rdfsolve.parser: Using chunked pagination for entity counts (step size: 300)

INFO:rdfsolve.parser:Using chunked pagination for entity counts (step size: 300)

2025-12-02 11:33:24 DEBUG rdfsolve.parser: Chunked entity count: chunk 1, rows=300, total=300

DEBUG:rdfsolve.parser:Chunked entity count: chunk 1, rows=300, total=300

2025-12-02 11:33:35 DEBUG rdfsolve.parser: Chunked entity count: chunk 2, rows=300, total=600

DEBUG:rdfsolve.parser:Chunked entity count: chunk 2, rows=300, total=600

2025-12-02 11:33:46 DEBUG rdfsolve.parser: Chunked entity count: chunk 3, rows=300, total=900

DEBUG:rdfsolve.parser:Chunked entity count: chunk 3, rows=300, total=900

2025-12-02 11:33:58 DEBUG rdfsolve.parser: Chunked entity count: chunk 4, rows=300, total=1200

import pandas as pd
import plotly.graph_objects as go

if not frequencies_with_instances_df.empty:
    df = frequencies_with_instances_df.copy()
    df["coverage_percent"] = pd.to_numeric(df["coverage_percent"], errors="coerce").fillna(0)
    df = df.sort_values("coverage_percent", ascending=False).reset_index(drop=True)

    def make_label(row):
        return (
            f"<b>{row['subject_class']}</b> "
            f"<span style='color:#888;'></span> "
            f"<i>{row['property']}</i> "
            f"<span style='color:#888;'></span> "
            f"<b>{row['object_class']}</b>"
        )

    df["styled_label"] = df.apply(make_label, axis=1)

    text_positions = ["outside" if v < 95 else "inside" for v in df["coverage_percent"]]
    custom_colorscale = [
        [0.0, "#d36e61"],
        [0.4, "#e5cdbd"],
        [0.7, "#e8e4cf"],
        [1.0, "#c3d9c0"],
    ]

    # Figure sizing
    bar_height = 26
    fig_height = min(2000, bar_height * len(df) + 200)

    fig = go.Figure(
        go.Bar(
            x=df["coverage_percent"],
            y=df["styled_label"],
            orientation="h",
            text=[f"{v:.1f}%" for v in df["coverage_percent"]],
            textposition=text_positions,
            marker={
                "color": df["coverage_percent"],
                "colorscale": custom_colorscale,
                "cmin": 0,
                "cmax": 100,
                "line": {"color": "white", "width": 0.6},
            },
            hovertemplate="<b>%{y}</b><br>Coverage: %{x:.1f}%<extra></extra>",
        )
    )

    fig.update_layout(
        title={
            "text": f"Schema Pattern Coverage for {dataset_name}",
            "x": 0.5,
            "font": {"size": 18},
        },
        xaxis={
            "title": "Coverage (%)",
            "range": [0, 100],  # fixed x-axis range
            "ticksuffix": "%",
            "showgrid": True,
            "gridcolor": "rgba(220,220,220,0.3)",
        },
        yaxis={
            "title": "",
            "autorange": "reversed",
            "automargin": True,
            "fixedrange": False,  # allow vertical zoom/pan
        },
        template="plotly_white",
        autosize=True,  # allow figure to scale with container
        height=fig_height,  # base height (will scale)
        margin={"t": 80, "b": 50, "l": 480, "r": 150},  # extra right margin for text
        plot_bgcolor="white",
        paper_bgcolor="white",
    )

    # Disable horizontal zoom/pan
    fig.update_xaxes(fixedrange=True)

    # Show figure with config for HTML export compatibility
    fig.show(
        config={
            "scrollZoom": True,
            "responsive": True,
            "toImageButtonOptions": {
                "format": "png",
                "filename": f"{dataset_name}_schema_coverage",
                "height": fig_height,
                "width": 600,
                "scale": 1,
            },
        }
    )

else:
    display(Markdown("**No coverage data to visualize**"))

# Generate LinkML directly from JSON-LD with custom schema URI
print("Regenerating LinkML schema from JSON-LD with custom schema URI...")

schema_name = f"{dataset_name}_schema"
custom_schema_uri = (
    f"http://jmillanacosta.github.io/rdfsolve/{dataset_name}/linkml"  # User-definable base URI
)

yaml_text = vp.to_linkml_yaml(
    schema_name=schema_name,
    schema_description=f"LinkML schema for {dataset_name} generated from JSON-LD",
    schema_base_uri=custom_schema_uri,
    filter_void_nodes=True,
)

# Save to LinkML YAML
linkml_file = os.path.join(exports_path, f"{dataset_name}_linkml_schema.yaml")
with open(linkml_file, "w", encoding="utf-8") as f:
    f.write(yaml_text)

print(f"LinkML YAML saved to: {linkml_file}")

Regenerating LinkML schema from JSON-LD with custom schema URI...

LinkML YAML saved to: /home/runner/work/rdfsolve/rdfsolve/notebooks/01_schema_extraction/../../docs/data/schema_extraction/pubchem.protein/pubchem.protein_linkml_schema.yaml

from linkml.generators.erdiagramgen import ERDiagramGenerator
from linkml_runtime.utils.schemaview import SchemaView

sv = SchemaView(linkml_file)
linkml_schema = sv.schema

display(
    Markdown(
        f"**Parsed LinkML schema:** Classes = {len(sv.all_classes())}, Slots = {len(sv.all_slots())}"
    )
)

# Build and display a Mermaid class diagram for the aopwikirdf LinkedML
mermaid_code = ERDiagramGenerator(linkml_file).serialize()

display(Markdown(mermaid_code))

erDiagram
BiopaxleveProtein {

}
Chebi17089 {

}
Pr000000001 {

}
Pr000000176 {

}
Pr000000814 {

}
Pr000001173 {

}
Pr000001206 {

}
Pr000001398 {

}
Pr000001587 {

}
Pr000001632 {

}
Pr000001654 {

}
Pr000001703 {

}
Pr000001961 {

}
Pr000001984 {

}
Pr000002103 {

}
Pr000003059 {

}
Pr000003064 {

}
Pr000003202 {

}
Pr000003270 {

}
Pr000003271 {

}
Pr000003416 {

}
Pr000003636 {

}
Pr000003676 {

}
Pr000003791 {

}
Pr000003906 {

}
Pr000004055 {

}
Pr000004105 {

}
Pr000004415 {

}
Pr000004515 {

}
Pr000004516 {

}
Pr000004712 {

}
Pr000005257 {

}
Pr000005584 {

}
Pr000005813 {

}
Pr000005950 {

}
Pr000006132 {

}
Pr000006133 {

}
Pr000007124 {

}
Pr000008457 {

}
Pr000008556 {

}
Pr000008615 {

}
Pr000008811 {

}
Pr000009267 {

}
Pr000009439 {

}
Pr000009771 {

}
Pr000009802 {

}
Pr000010165 {

}
Pr000010229 {

}
Pr000010268 {

}
Pr000010415 {

}
Pr000011334 {

}
Pr000011416 {

}
Pr000012466 {

}
Pr000012467 {

}
Pr000012479 {

}
Pr000012745 {

}
Pr000013479 {

}
Pr000014284 {

}
Pr000014373 {

}
Pr000015167 {

}
Pr000016481 {

}
Pr000016695 {

}
Pr000017300 {

}
Pr000023005 {

}
Pr000032150 {

}
Pr000032431 {

}
Pr000035207 {

}
PrA2ASI5 {

}
PrA5A4K9 {

}
PrB0BNE5 {

}
PrB0V2N1 {

}
PrD3ZTE0 {

}
PrE9Q4S1 {

}
PrF1M391 {

}
PrO15164 {

}
PrO15438 {

}
PrO15552 {

}
PrO35881 {

}
PrO55023 {

}
PrO95838 {

}
PrP00356 {

}
PrP00439 {

}
PrP00760 {

}
PrP01112 {

}
PrP04800 {

}
PrP08276 {

}
PrP09874 {

}
PrP0AG80 {

}
PrP10064 {

}
PrP11157 {

}
PrP13639 {

}
PrP15145 {

}
PrP15385 {

}
PrP15539 {

}
PrP16390 {

}
PrP19205 {

}
PrP19785 {

}
PrP20420 {

}
PrP20612 {

}
PrP21803 {

}
PrP22888 {

}
PrP23141 {

}
PrP24524 {

}
PrP26897 {

}
PrP28843 {

}
PrP31041 {

}
PrP32501 {

}
PrP41180 {

}
PrP42681 {

}
PrP42858 {

}
PrP43003 {

}
PrP43352 {

}
PrP43354 {

}
PrP46406 {

}
PrP47196 {

}
PrP48169 {

}
PrP48442 {

}
PrP48443 {

}
PrP48544 {

}
PrP48730 {

}
PrP49657 {

}
PrP50114 {

}
PrP50571 {

}
PrP51577 {

}
PrP51617 {

}
PrP51788 {

}
PrP51880 {

}
PrP52186 {

}
PrP53778 {

}
PrP55011 {

}
PrP56221 {

}
PrP56657 {

}
PrP56658 {

}
PrP56696 {

}
PrP61887 {

}
PrP70340 {

}
PrP70579 {

}
PrP70597 {

}
PrP97931 {

}
PrP98106 {

}
PrQ01064 {

}
PrQ05438 {

}
PrQ05816 {

}
PrQ05940 {

}
PrQ07973 {

}
PrQ09128 {

}
PrQ14449 {

}
PrQ15119 {

}
PrQ15759 {

}
PrQ15831 {

}
PrQ28691 {

}
PrQ2MKA5 {

}
PrQ4G050 {

}
PrQ4G072 {

}
PrQ4V8J7 {

}
PrQ5I0E9 {

}
PrQ5XPT3 {

}
PrQ60613 {

}
PrQ61096 {

}
PrQ62413 {

}
PrQ62968 {

}
PrQ63484 {

}
PrQ6P8U6 {

}
PrQ6U1I9 {

}
PrQ7ZUC7 {

}
PrQ80W21 {

}
PrQ86UX6 {

}
PrQ8BYR2 {

}
PrQ8CA95 {

}
PrQ8CIN4 {

}
PrQ8CJF9 {

}
PrQ8JH70 {

}
PrQ8R429 {

}
PrQ8TCT1 {

}
PrQ90733 {

}
PrQ924T8 {

}
PrQ92993 {

}
PrQ96HU8 {

}
PrQ99JT2 {

}
PrQ9BZZ2 {

}
PrQ9D1P2 {

}
PrQ9D8I2 {

}
PrQ9H3R0 {

}
PrQ9H7Z7 {

}
PrQ9HB14 {

}
PrQ9JHF7 {

}
PrQ9NRG4 {

}
PrQ9QUR6 {

}
PrQ9QXX3 {

}
PrQ9R0P3 {

}
PrQ9R0S2 {

}
PrQ9R1E6 {

}
PrQ9UHI7 {

}
PrQ9UIQ6 {

}
PrQ9UM07 {

}
PrQ9WTR1 {

}
PrQ9WVJ0 {

}
PrQ9Y4K4 {

}
PrQ9Y5Z0 {

}
PrQ9Z0V1 {

}
Sio010043 {

}
VocabularyProtein {

}

BiopaxleveProtein ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Chebi17089 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000000001 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000000176 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000000814 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001173 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001206 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001398 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001587 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001632 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001654 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001703 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001961 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000001984 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000002103 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003059 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003064 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003202 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003270 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003271 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003416 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003636 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003676 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003791 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000003906 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000004055 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000004105 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000004415 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000004515 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000004516 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000004712 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000005257 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000005584 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000005813 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000005950 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000006132 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000006133 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000007124 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000008457 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000008556 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000008615 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000008811 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000009267 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000009439 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000009771 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000009802 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000010165 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000010229 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000010268 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000010415 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000011334 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000011416 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000012466 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000012467 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000012479 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000012745 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000013479 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000014284 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000014373 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000015167 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000016481 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000016695 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000017300 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000023005 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000032150 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000032431 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Pr000035207 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrA2ASI5 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrA5A4K9 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrB0BNE5 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrB0V2N1 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrD3ZTE0 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrE9Q4S1 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrF1M391 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrO15164 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrO15438 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrO15552 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrO35881 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrO55023 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrO95838 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP00356 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP00439 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP00760 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP01112 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP04800 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP08276 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP09874 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP0AG80 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP10064 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP11157 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP13639 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP15145 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP15385 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP15539 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP16390 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP19205 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP19785 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP20420 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP20612 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP21803 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP22888 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP23141 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP24524 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP26897 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP28843 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP31041 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP32501 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP41180 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP42681 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP42858 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP43003 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP43352 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP43354 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP46406 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP47196 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP48169 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP48442 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP48443 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP48544 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP48730 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP49657 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP50114 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP50571 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP51577 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP51617 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP51788 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP51880 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP52186 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP53778 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP55011 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP56221 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP56657 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP56658 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP56696 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP61887 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP70340 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP70579 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP70597 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP97931 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrP98106 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ01064 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ05438 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ05816 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ05940 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ07973 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ09128 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ14449 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ15119 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ15759 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ15831 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ28691 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ2MKA5 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ4G050 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ4G072 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ4V8J7 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ5I0E9 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ5XPT3 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ60613 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ61096 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ62413 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ62968 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ63484 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ6P8U6 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ6U1I9 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ7ZUC7 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ80W21 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ86UX6 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8BYR2 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8CA95 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8CIN4 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8CJF9 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8JH70 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8R429 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ8TCT1 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ90733 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ924T8 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ92993 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ96HU8 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ99JT2 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9BZZ2 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9D1P2 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9D8I2 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9H3R0 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9H7Z7 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9HB14 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9JHF7 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9NRG4 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9QUR6 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9QXX3 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9R0P3 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9R0S2 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9R1E6 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9UHI7 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9UIQ6 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9UM07 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9WTR1 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9WVJ0 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9Y4K4 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9Y5Z0 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
PrQ9Z0V1 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
Sio010043 ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"
VocabularyProtein ||--|o Pr000000001 : "vocabulary_has_Similar_Protein"

json_path = os.path.join(exports_path, f"{dataset_name}_schema.json")
csv_path = os.path.join(exports_path, f"{dataset_name}_schema.csv")

# Export CSV from frequencies
frequencies_df.to_csv(csv_path, index=False)

# Export JSON derived from JSON-LD (maintains consistency)
with open(json_path, "w", encoding="utf-8") as fh:
    json.dump(vp.to_json(filter_void_nodes=True), fh, indent=2)

print(f"CSV exported to: {csv_path}")
print(f"JSON exported to: {json_path}")

CSV exported to: /home/runner/work/rdfsolve/rdfsolve/notebooks/01_schema_extraction/../../docs/data/schema_extraction/pubchem.protein/pubchem.protein_schema.csv
JSON exported to: /home/runner/work/rdfsolve/rdfsolve/notebooks/01_schema_extraction/../../docs/data/schema_extraction/pubchem.protein/pubchem.protein_schema.json

# Export collected SPARQL queries as TTL
queries_path = os.path.join(exports_path, f"{dataset_name}_sparql_queries.ttl")
queries = SparqlHelper.get_collected_queries()

if queries:
    ttl_content = SparqlHelper.export_queries_as_ttl(
        output_file=queries_path,
        base_uri=f"https://github.com/jmillanacosta/rdfsolve/sparql/{dataset_name}/",
        dataset_name=dataset_name,
    )
    print(f"Exported {len(queries)} SPARQL queries to: {queries_path}")
else:
    print("No SPARQL queries were collected")

Exported 57028 SPARQL queries to: /home/runner/work/rdfsolve/rdfsolve/notebooks/01_schema_extraction/../../docs/data/schema_extraction/pubchem.protein/pubchem.protein_sparql_queries.ttl

	subject_class	subject_uri	property	property_uri	object_class	object_uri
0	pr:000000001	http://purl.obolibrary.org/obo/PR_000000001	vocabulary:hasSimilarProtein	http://rdf.ncbi.nlm.nih.gov/pubchem/vocabulary...	pr:000000001	http://purl.obolibrary.org/obo/PR_000000001
1	pr:000000001	http://purl.obolibrary.org/obo/PR_000000001	vocabulary:hasSimilarProtein	http://rdf.ncbi.nlm.nih.gov/pubchem/vocabulary...	biopaxleve:Protein	http://www.biopax.org/release/biopax-level3.ow...
2	pr:000000001	http://purl.obolibrary.org/obo/PR_000000001	vocabulary:hasSimilarProtein	http://rdf.ncbi.nlm.nih.gov/pubchem/vocabulary...	vocabulary:Protein	http://rdf.ncbi.nlm.nih.gov/pubchem/vocabulary...
3	pr:000000001	http://purl.obolibrary.org/obo/PR_000000001	vocabulary:hasSimilarProtein	http://rdf.ncbi.nlm.nih.gov/pubchem/vocabulary...	pr:000000732	http://purl.obolibrary.org/obo/PR_000000732
4	pr:000000001	http://purl.obolibrary.org/obo/PR_000000001	vocabulary:hasSimilarProtein	http://rdf.ncbi.nlm.nih.gov/pubchem/vocabulary...	pr:000000785	http://purl.obolibrary.org/obo/PR_000000785

	subject_class	property	object_class	coverage_percent
21946	pr:P26897	vocabulary:hasSimilarProtein	biopaxleve:Protein	100.0
21947	pr:P26897	vocabulary:hasSimilarProtein	vocabulary:Protein	100.0
14005	pr:000032431	vocabulary:hasSimilarProtein	vocabulary:Protein	100.0
32187	pr:Q4G050	vocabulary:hasSimilarProtein	biopaxleve:Protein	100.0
32188	pr:Q4G050	vocabulary:hasSimilarProtein	vocabulary:Protein	100.0

pubchem.protein Schema Extraction¶

Exports¶

Cache Control¶

Discover or get VoID Schema¶

Schema Discovery and Exports Workflow¶

Workflow Steps:¶

Schema Pattern Coverage Analysis¶

Schema Pattern Instance Collection¶

LinkML (derived from JSON-LD)¶